Head to head
Esc

Models · slot A

to navigate to pick

FLUX.2 [max] Black Forest Labs Wan 2.7 Pro Alibaba

Settled by community votes across 20 shared challenges, with an AI judge weighing in on each.

FLUX.2 [max]

25.9 arena score

#10 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

20.7 arena score

#38 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.2 [max]

66.7%

win rate

Ties

0.0%

Wan 2.7 Pro

33.3%

win rate

66.7% 0.0% ties 33.3%
Shared challenges 20

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent photorealistic rendering of the leather texture on the red book.
  • + Accurately represents glass refractions and reflections on the table.
  • + Perfect adherence to lighting and composition instructions.
  • The glass cube is missing one side (the front face is completely invisible/non-existent), making it look like an open frame.

Wan 2.7 Pro

  • + Realistic glass thickness and distinct edges showing a full cube structure.
  • + High-quality texture on the wooden table and the fern leaves.
  • + Accurate placement of all requested elements including the soft window light.
  • The reflection of the sphere on the bottom of the cube doesn't quite match the top texture of the sphere.

Verdict: Both models followed the prompt perfectly, but Wan 2.7 Pro is the winner because it successfully rendered a complete glass cube with visible depth and edge thickness. FLUX.2 [max] produced a more aesthetically pleasing book, but failed to render the front face of the cube, making the sphere appear to be sitting in an open display case rather than a closed glass box.

Man and Car in California

Editing
Edit instruction

“Make a photo of the man driving the car down the California coastline”

Source
FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent preservation of the man's identity, clothing, and hairstyle
  • + High fidelity to the original car's design and lighting
  • + Perfectly captures the requested California coastline background
  • The man's scale relative to the car is slightly small

Wan 2.7 Pro

  • + Beautiful warm sunset lighting that blends well across the scene
  • + Effective coastal scenery composition
  • Completely failed to preserve the man's identity, replacing him with a different person
  • The person in the seat is too small for the scale of the interior

Verdict: FLUX.2 [max] is the clear winner as it successfully combined both source images, maintaining the specific person's appearance, clothing, and the exact model of the car. Wan 2.7 Pro provided a generic scene with a different person, failing the source preservation aspect of the image editing challenge.

Candid Street Photography

Text-to-Image

“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent adherence to the 'motion blur from passing cars' prompt
  • + Very realistic skin texture and hands
  • + Strong cinematic lighting and depth of field consistent with a 50mm lens
  • Slightly tight framing despite the 'imperfect framing' request

Wan 2.7 Pro

  • + Effective 'imperfect framing' and candid composition
  • + Beautiful reflections on the wet pavement
  • + Natural elder facial features
  • Failed to include motion blur on the background vehicles
  • Lacks the specific 50mm shallow depth of field feel
  • Occasional anatomical issues with hands clutching the bicycle

Verdict: FLUX.2 [max] captures all technical aspects of the prompt, particularly the motion blur and 50mm depth of field, resulting in a more cinematic and realistic photograph. Wan 2.7 Pro handles the reflections well but fails to execute the motion blur and has less precise detail in the hands and bicycle mechanics.

Fantasy Warrior

Text-to-Image

“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent character expression and lifelike eyes.
  • + Extremely high fidelity on armor engravings and material weathering.
  • + Strong adherence to the shallow depth of field and bokeh sparks request.
  • The braids are somewhat hidden behind the head rather than being a prominent feature.

Wan 2.7 Pro

  • + Very accurate representation of hair braided with beads as requested.
  • + Good lighting interaction between the torches and the armor plates.
  • + Balanced composition showing more of the leather strap detailing.
  • Skin texture is slightly smoother and less detailed compared to Model A.
  • The 'bokeh sparks' look more like static fire light sources in the background.

Verdict: FLUX.2 [max] wins due to its superior textural detail, particularly in the weathered armor and the intensity of the character's gaze. While Wan 2.7 Pro followed the hair braiding instructions more visibly, FLUX.2 [max] achieved a more cinematic, high-quality look that better captured the 'battle-worn' aesthetic.

Modern Clean Menu

Text-to-Image

“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Stronger adherence to the color-coded section requirement with bold accents
  • + Clean, high-contrast layout that looks professional
  • + Excellent use of bold sans-serif fonts as requested
  • Internal logic is poor as it labels a burger under 'Mains' and mentions pizza under 'Mains'
  • Image grid is inconsistent with labels, showing burgers next to appetizers and pizza

Wan 2.7 Pro

  • + Excellent photo-realistic food quality in the grid
  • + Better composition with a realistic setting including props like a pen and salt
  • + Includes specific details like a QR code and restaurant branding
  • Text rendering is slightly blurry and less professional than Model A
  • Failed to properly organize sections into Appetizers/Pizza/Mains as vertical headers
  • The 'Bread & Bowl' title limits the scope compared to the requested sections

Verdict: FLUX.2 [max] creates a design that looks like a real digital menu file with a very clean, professional layout and bold typography, though it struggles with the logic of placing specific food items in the right sections. Wan 2.7 Pro produces a more aesthetically pleasing lifestyle image with beautiful food photography and a realistic context, but the menu itself is harder to read and doesn't follow the requested section structure as clearly as Model A. FLUX.2 is the winner for its superior graphic design clarity and prompt adherence regarding layout and font.

Magic Burger Explosion: Fiery Photorealism Challenge

Text-to-Image

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

FLUX.2 [max]
Wan 2.7 Pro
100% wins 0% ties 0% wins

AI Judge Analysis

FLUX.2 [max]

  • + Excellent photorealistic texture on the bun and patty
  • + Clean and highly legible graphic design layout
  • + Smooth, natural integration of the floating sauce
  • The 'exploded' effect is less dynamic than the competitor
  • Misses the fiery/glowing effect on the price text

Wan 2.7 Pro

  • + Highly dynamic 'deconstructed' composition with great motion
  • + Incorporates more varied ingredients like onions and cucumbers
  • + Closely follows the atmospheric prompt with fiery effects on all text elements
  • The cheese has a slightly plastic or artificial appearance
  • The bottom bun looks a bit flat and less detailed than the top
  • The lettuce leaf looks like a single clip-art element rather than part of a cohesive burger

Verdict: FLUX.2 [max] produces a more professional and realistic food advertisement with superior textures, but it is more conservative with the 'exploded' motion. Wan 2.7 Pro better captures the energy and specific atmospheric requirements of the prompt, including the fiery text effects and a more dramatic deconstruction, making it the more visually exciting choice despite slightly lower realism in the food textures.

Chalkboard Menu

Text-to-Image

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent chalk texture on the lettering with realistic smudges and grain.
  • + Highly realistic lighting and atmosphere that feels like a real café.
  • + Accurately renders all requested text including the truncated menu item.
  • The handwriting leans slightly towards a digital font feel compared to the variations in Model B.
  • The spacing between the top lines is a bit tight.

Wan 2.7 Pro

  • + Perfectly captures the 'handwritten cursive' style requested for the title.
  • + The text layout is clean, balanced, and very easy to read while maintaining a chalk aesthetic.
  • + Successfully completes the truncated prompt text into logical meal names.
  • The chalk texture on the letters is a bit too clean and uniform, looking slightly digital.
  • The background café elements are a bit stereotypical and busy compared to the focused lighting of Model A.

Verdict: Both models followed the complex text requirements perfectly, which is an impressive feat. FLUX.2 [max] wins on pure photorealism and texture, as the chalk looks authentically dusty and the lighting is superior. However, Wan 2.7 Pro followed the stylistic instruction for 'elegant cursive' in the title much more effectively than FLUX.2 did.

Pose & Character Mashup

Editing
Edit instruction

“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”

Source
FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent character replication, including the specific face, sunglasses, scarf, and clothing details from Image 2.
  • + Accurately places the character in the lighting and environment of Image 1.
  • + Successfully translates the complex balance and limb positioning of the pose from Image 1.
  • The feet and toes show some structural AI artifacts.
  • The text on the shirt is partially garbled compared to the source.

Wan 2.7 Pro

  • + Perfect preservation of the original Image 1 background and colors.
  • Completely failed the edit instruction to change the character.
  • The output is identical to Image 1 with no elements of Image 2 integrated.
  • Did not perform any character replacement.

Verdict: FLUX.2 [max] successfully performed the complex task of character replacement while maintaining pose and environment, accurately importing the person, sunglasses, scarf, and black clothing from Image 2 into the dynamic pose of Image 1. Wan 2.7 Pro failed entirely, returning the original Image 1 without any modifications. FLUX.2 [max] is the clear winner for following all multi-step instructions.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent cinematic lighting and atmosphere.
  • + High level of detail in the astronaut suit and horse texture.
  • + Strong composition with the galaxy background and asteroid base.
  • Failed to follow the specific spatial instruction for the horse to be on top of the astronaut.

Wan 2.7 Pro

  • + Clean rendering of the astronaut and horse.
  • + Good scale contrast between the subject and the planet background.
  • Failed to follow the specific spatial instruction for the horse to be on top of the astronaut.
  • Anatomical issues with the horse's legs, especially the front right leg.
  • Flat lighting compared to the rival model.

Verdict: Both FLUX.2 [max] and Wan 2.7 Pro failed the primary logic challenge of placing the horse on top of the astronaut, both defaulting to the standard 'astronaut riding a horse' trope. However, FLUX.2 [max] is the superior image due to its significantly better cinematic lighting, detailed environment, and anatomical correctness, whereas Wan 2.7 Pro suffers from awkward horse limb positioning and less impressive textures.

Outfit Transfer Challenge

Editing
Edit instruction

“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”

Source
FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Perfectly replicates the outfit from Image 2, including the specific pattern of the scarf and the coat style.
  • + Successfully matches the lighting and skin tones of the original subject to the new clothing.
  • + Retains fine details of the jewelry like the watch and ring from Image 2.
  • The facial features are slightly altered to look more mature/different than Image 1.
  • Changes the background color grading and sky compared to Image 1.

Wan 2.7 Pro

  • + Maintains the full-body composition and background of Image 1 much better.
  • + The subject's facial appearance and skin patterns remain very close to the original.
  • Completely fails to use the clothing from Image 2, generating a random gold-patterned jacket instead.
  • The hand integration on the wood post is messy with anatomical distortions.

Verdict: FLUX.2 [max] significantly outperformed the competition on the most difficult part of the prompt by perfectly replicating the elaborate outfit from Image 2, whereas Wan 2.7 Pro generated a completely unrelated suit. While Wan 2.7 Pro was better at preserving the original background and pose, its failure to adhere to the target clothing makes it unsuccessful for this specific editing task.

The Capybara Taxi Driver

Text-to-Image

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

FLUX.2 [max]
Wan 2.7 Pro
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.2 [max]

  • + Excellent photorealistic lighting on the capybara's fur and the interior dashboard.
  • + Composition clearly places the passenger in the back seat as requested.
  • The capybara has realistic human hands instead of capybara paws.
  • The passenger is looking at her phone but appears slightly out of focus compared to the driver.

Wan 2.7 Pro

  • + Successfully renders animal-like paws on the steering wheel.
  • + The passenger has a perfect bored expression that fits the prompt's narrative.
  • The passenger is sitting in the front passenger seat instead of the back seat.
  • The transition between the capybara's head and the jacket looks less natural than in the other model.

Verdict: FLUX.2 [max] creates a more cinematic and realistic lighting environment with a correct spatial arrangement of the passenger in the back seat, though it fails on the 'paws' requirement by giving the animal human hands. Wan 2.7 Pro correctly interprets the anatomy of the capybara's paws and the bored expression of the passenger, but fails the foundational compositional instruction of placing the passenger in the back seat. FLUX.2 [max] is the winner for better overall image coherence and adherence to the interior layout of a taxi.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent cinematic lighting with a realistic 3D feel.
  • + Perfect text rendering with glowing gothic font effects.
  • + Clean and spooky atmosphere that balances realism with graphic design.
  • The thorns and webs are somewhat tucked behind the parchment edge rather than acting as a prominent border.
  • Minimalistic background compared to the other model.

Wan 2.7 Pro

  • + Rich, intricate border design featuring thorns, webs, and extra thematic elements.
  • + Highly creative illustration style that feels like a vintage storybook.
  • + Includes all requested elements plus thematic additions like lanterns and a cauldron.
  • Text layout is a bit cluttered with extra non-prompted text like 'Est. 1847'.
  • The drawing style is more 'illustrated' than 'cinematic' as requested.

Verdict: FLUX.2 [max] creates a more professional and modern 'cinematic' invitation with superior lighting and clean typography. Wan 2.7 Pro offers a much more detailed and illustrative 'vintage' gothic look with an impressive border, though it adds unrequested text and has a flatter, more cartoon-like appearance compared to FLUX's realistic depth.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.2 [max]
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent preservation of the source background, clothing, and facial features.
  • + The hair texture and lighting blend seamlessly with the original image's atmosphere.
  • + Natural integration with the existing sideburns and beard.
  • The hairline on the forehead is slightly high and lacks fine transitional baby hairs.

Wan 2.7 Pro

  • + Successfully adds a full head of hair that matches the character's aesthetic.
  • + Maintains the facial identity and almost all background details perfectly.
  • The hair appears slightly flatter in volume compared to Model A.
  • A subtle digital artifact or smudging is visible where the top of the hair meets the sky.

Verdict: Both models performed exceptionally well at this image editing task, preserving the original subject's identity, lighting, and environment perfectly. FLUX.2 [max] is the preferred winner because the hair volume and texture felt more natural and had better integration with the scalp and forehead than Wan 2.7 Pro.

Isometric Miniature Diorama Scenes

Text-to-Image

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent adherence to the isometric perspective and diorama base request.
  • + Perfect text rendering and layout for 'JAPAN SUSHI' and the flag.
  • + Clean, minimalist composition that looks like a professional 3D render.
  • The textures on the sushi are a bit flat and plastic-like compared to Model B.
  • Chopsticks are slightly fused with the wooden board.

Wan 2.7 Pro

  • + Superb texture work with realistic subsurface scattering on the fish and ikura.
  • + Includes more detailed sushi variety and garnishes like the shiso leaf.
  • + High visual clarity and soft, pleasing lighting.
  • Failed to include the requested 'raised diorama base', placing the plate directly on the ground.
  • Added extra text 'Authentic Japanese Cuisine' which was not in the prompt.
  • Random floating artifacts in the upper corners and stray chopsticks at the bottom edge.

Verdict: FLUX.2 [max] followed the structural instructions much better, correctly creating the 45-degree isometric diorama base and perfectly centering the requested text. While Wan 2.7 Pro has superior material textures and more appetizing sushi models, it failed the diorama requirement and introduced several compositional errors like floating artifacts and cut-off chopsticks.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent caricature style with exaggerated proportions typical of the genre.
  • + Highly cohesive scene that blends the TV anchor desk into a hockey rink seamlessly.
  • + Captures the subject's likeness and original clothing (denim shirt) accurately while stylizing it.
  • The text 'JEMER EWS' is slightly garbled and contains nonsense characters.
  • The subject's eyes were changed from brown to blue.

Wan 2.7 Pro

  • + Includes specific 'dog love' and 'hockey' labels for clarity.
  • + Good facial expression that matches the 'exaggerated and humorous' instruction.
  • + The dogs are wearing hockey jerseys, which is a clever creative touch.
  • The 'microphone hockey stick' hybrid is visually confusing and poorly rendered.
  • Low quality rendering on the hands and speech bubbles (black lines bleeding).
  • The caricature style is less professional and polished compared to the competitor.

Verdict: FLUX.2 [max] produced a high-quality, professional caricature that creatively merged all requested elements into a single scene (a news desk on an ice rink). While Wan 2.7 Pro attempted a humorous approach with hockey jerseys on the dogs, the overall execution was messy, especially with the strange microphone-stick hybrid. FLUX also did a better job of preserving the subject's facial features and original outfit.

Adorable Baby Animals in Sunny Meadow

Text-to-Image

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Perfectly captures the atmospheric god rays and soft sunrise glow.
  • + Superior rendering of dew sparkles on the meadow grass.
  • + Anatomically correct paws and features for all four animals.
  • Butterflies are slightly less prominent compared to the other model.

Wan 2.7 Pro

  • + Dynamic interaction between the animals with a playful tumbling feel.
  • + Very high contrast and sharpness on the fur textures.
  • Obvious anatomical errors, specifically the kitten having an extra leg/paw visible beneath its chest.
  • The kitten's tail appears to be merged into the fox's body incorrectly.
  • The lighting is bit more 'digital' and less naturally integrated into the environment.

Verdict: FLUX.2 [max] is the winner due to its superior anatomical accuracy and beautiful atmospheric rendering, perfectly capturing the dew sparkles and soft god rays requested. While Wan 2.7 Pro has a lovely composition, it suffers from significant AI artifacts including a kitten with a fifth leg and merged body parts.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent adherence to the Ghibli art style with soft, rounded character features.
  • + Captures the wash-out pastel color palette and dreamy textures requested.
  • + The man's expression is perfectly stylized into a classic anime aesthetic.
  • The woman in the foreground's facial structure is significantly altered from the source image.
  • Lacks some of the vibrant contrast seen in the original Ghibli films, feeling a bit too hazy.

Wan 2.7 Pro

  • + Strong watercolor texture that feels hand-painted.
  • + Preserves the original facial structures and expressions more accurately than Model A.
  • + Great balance of warm, nostalgic lighting.
  • The style feels more like a western comic watercolor than a Studio Ghibli illustration.
  • The faces remain a bit too realistic for the requested anime-inspired prompt.

Verdict: FLUX.2 [max] captures the Studio Ghibli aesthetic much better by simplifying facial features into the iconic anime style, whereas Wan 2.7 Pro produces a high-quality watercolor painting that retains too much realism in the characters' faces. While Wan 2.7 Pro preserves the source likeness better, FLUX.2 [max] is the winner for fulfilling the specific stylistic transformation requested in the prompt.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.2 [max]
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Successfully added wind movement to hair and numerous flying leaves.
  • + Maintains identical facial features and clothing from the source image.
  • + The large leaves in the foreground create a strong sense of depth.
  • The wind direction on the hair (blowing left) slightly contradicts the direction suggested by the leaves.
  • The leaves in the foreground are a bit blurry compared to the rest of the sharp image.

Wan 2.7 Pro

  • + Excellent depiction of wind-blown hair that feels natural and energetic.
  • + Great distribution of falling and flying leaves across the foreground and background.
  • + High fidelity preservation of the woman and dog from the source image.
  • The lighting on the dog's back is slightly more yellow/brightened compared to the source.
  • Some leaves look a bit static rather than having motion blur.

Verdict: Both models performed excellently in this image editing task, preserving the original subjects almost perfectly while adding the requested motion. FLUX.2 [max] provides a more dramatic foreground effect with larger leaves, while Wan 2.7 Pro creates a more cohesive overall feeling of a windy day with a more natural wind effect on the hair.

Vintage Cafe Logo

Text-to-Image

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography including the grave accent in 'Caffè'
  • + Minimalist and clean vector design
  • + Authentic subtle paper texture as requested
  • The Cloche illustration is slightly too simple/flat compared to the text depth

Wan 2.7 Pro

  • + Detailed illustrative style on the cloche and steam
  • + Good use of the requested banner and warm brown tones
  • Misspelled the name as 'Florion'
  • Included distracting peripheral graphics outside the main logo circle
  • The layout is a bit cluttered compared to the minimalist request

Verdict: FLUX.2 [max] followed the prompt more accurately, particularly with the text rendering of 'Caffè Florian' and the minimalist vector style. While Wan 2.7 Pro had a more detailed illustration for the cloche, it failed on the spelling of the brand name and included extra elements that detracted from the logo's impact.

Apollo 11: Journey to Tranquility

Text-to-Image

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

FLUX.2 [max]
Wan 2.7 Pro

AI Judge Analysis

FLUX.2 [max]

  • + Excellent typography and spelling of astronaut names
  • + Clean, sophisticated vector illustrations with nice use of shadow
  • + Clear logical flow through tiled boxes
  • Repeated 'Earth Orbit' label across multiple icons
  • Confusing overlapping lines in the descent/landing panels

Wan 2.7 Pro

  • + Perfect adherence to all 6 requested steps with unique icons for each
  • + Strong use of the NASA-inspired color palette
  • + Includes impressive technical details and factual data
  • Minor spelling error in 'DESCRIPT' (Descent)
  • Space shuttle icon for launch is historically inaccurate for Apollo 11

Verdict: Wan 2.7 Pro followed the complex multi-step prompt almost perfectly, creating a comprehensive and aesthetically pleasing vertical infographic. While FLUX.2 [max] produced more aesthetically refined individual illustrations, it failed to capture the distinct sequence of steps, repeating labels and omitting the specific progression requested.

Next steps

Explore each model